Bioprocess and Biosystems Engineering

, Volume 31, Issue 6, pp 631–640 | Cite as

Clustering hybrid regression: a novel computational approach to study and model biohydrogen production through dark fermentation

Original Paper


Clustering hybrid regression (CHR) approach was developed and evaluated using data from H2-producing glucose-based, suspended-cell bioreactor operated for 5 months. The aim was to describe the relationship between metabolic end products and H2-production rate. Self-organizing maps (SOM) were used to better visualize the dataset and to detect main metabolic patterns in bioprocess data. SOM detected three distinct metabolic patterns with butyrate, acetate and ethanol as dominant metabolites, respectively. Butyrate dominated metabolism was related to high H2 production, while acetate and ethanol dominated metabolisms resulted in low H2 production. CHR models performed well [mean square error (MSE) 0.55 and 0.56] in modeling the H2-production rate. The results validate the suitability of the CHR approach in describing the bioprocess behavior and in the modeling of H2 production rate. The developed model can help in discovering key metabolic interactions and suitable process parameters from complex datasets, and increase the understanding of the bioprocesses occurring in engineered and natural environments.


Biohydrogen Bioprocess modeling Clustering hybrid regression (CHR) K-means Self-organizing maps (SOM) 



This research was funded by the Academy of Finland (HYDROGENE project, no. 107425), Nordic Energy Research (BIOHYDROGEN project, no. 28–02) and Tampere University of Technology Graduate School (P. E. P. Koskinen). The work was also supported by the Academy of Finland (application number 213462, Finnish Programme for Centers of Excellence in Research 2006–2011). The technical assistance of Soong Linhao and Aino-Maija Lakaniemi is highly acknowledged.


  1. 1.
    Bockris JOM (2002) The origin of ideas on a hydrogen economy and its solution to the decay of the environment. Int J Hydrogen Energy 27:731–740CrossRefGoogle Scholar
  2. 2.
    Das D, Veziroğlu TN (2001) Hydrogen production by biological processes: a survey of literature. Int J Hydrogen Energy 26:13–28CrossRefGoogle Scholar
  3. 3.
    Benemann J (1996) Hydrogen biotechnology: progress and prospects. Nat Biotechnol 14:1101–1103CrossRefGoogle Scholar
  4. 4.
    Kapdan IK, Kargi F (2006) Bio-hydrogen production from waste materials. Enzyme Microb Tech 38:569–582CrossRefGoogle Scholar
  5. 5.
    Li C, Fang HHP (2007) Fermentative hydrogen production and wastewater and solid wastes by mixed cultures. Crit Rev Env Sci Technol 37:1–39CrossRefGoogle Scholar
  6. 6.
    Lin CY, Chang RC (2004) Fermentative hydrogen production at ambient temperature. Int J Hydrogen Energy 29:715–720CrossRefGoogle Scholar
  7. 7.
    Rodriguez J, Kleerebezem R, Lema JM, van Loosdrecht MC (2006) Modeling product formation in anaerobic mixed culture fermentations. Biotechnol Bioeng 93:592–606CrossRefGoogle Scholar
  8. 8.
    Bailey EJ (1998) Mathematical modeling and analysis in biochemical engineering: past accomplishments and future opportunities. Biotechnol Prog 14:8–20CrossRefGoogle Scholar
  9. 9.
    Bernard O, Bastin G (2005) On the estimation of the pseudo-stoichiometric matrix for macroscopic mass balance modelling of biotechnological processes. Math Biosci 193:51–77CrossRefGoogle Scholar
  10. 10.
    Husain A (1998) Mathematical models of the kinetics of anaerobic digestion—a selected review. Biomass Bioenerg 14:561–571CrossRefGoogle Scholar
  11. 11.
    McCarty PL, Mosey FE (1991) Modelling of anaerobic digestion processes (a discussion of concepts). Wat Sci Technol 24(8):123–129Google Scholar
  12. 12.
    Ramkrishna D, Amundson NR (2004) Mathematics in chemical engineering: a 50 year introspection. AIChE J 50:7–23CrossRefGoogle Scholar
  13. 13.
    Rani KY, Rao VSR (1999) Control of fermenters—a review. Bioprocess Eng 21:77–78CrossRefGoogle Scholar
  14. 14.
    Rapaport A, Dochain D (2005) Interval observers for biochemical processes with uncertain kinetics and inputs. Math Biosci 193:235–253CrossRefGoogle Scholar
  15. 15.
    Batstone DJ, Keller J, Angelidaki I, Kalyuzhnyi SV, Pavlostathis SG, Rozzi A, Sanders WTM, Siegrist H, Vavilin VA (2002) Anaerobic digestion model no. 1 (ADM1), IWA Task Group for mathematical modelling of anaerobic digestion processes. IWA Publishing, LondonGoogle Scholar
  16. 16.
    Blumensaat F, Keller J (2005) Modelling of two-stage anaerobic digestion using the IWA Anaerobic digestion model no. 1 (ADM1). Water Res 39:171–183CrossRefGoogle Scholar
  17. 17.
    Kalyuzhnyi SV (1997) Batch anaerobic digestion of glucose and its mathematical modeling. II. Description, verification and application of model. Bioresour Technol 59:249–258CrossRefGoogle Scholar
  18. 18.
    Parker WJ (2005) Application of the ADM1 model to advanced anaerobic digestion. Bioresour Technol 96:832–1842CrossRefGoogle Scholar
  19. 19.
    Nikhil, Visa A, Yli-Harja O, Lin CY, Puhakka JA (2008) Application of CHR approach to model xylose-based fermentative hydrogen production. Energ Fuel 22(1):128–133CrossRefGoogle Scholar
  20. 20.
    Koskinen PEP, Kaksonen AH, Puhakka JA (2007) The relationship between instability of H2 production and compositions of bacterial communities within a dark fermentation fluidized-bed bioreactor. Biotechnol Bioeng 97(4):742–758CrossRefGoogle Scholar
  21. 21.
    Kohonen T (1995) Self-organizing maps. Springer series in information sciences, vol 30. Springer, BerlinGoogle Scholar
  22. 22.
    Simula O, Kangas J (1995) Process monitoring and visualization using self-organizing maps. Neural networks for chemical engineers. Computer-aided chemical engineering. Elsevier, Amsterdam, pp 377–390Google Scholar
  23. 23.
    Kaski S (1997) Data exploration using self-organizing maps. DTech Thesis. Helsinki University of Technology, FinlandGoogle Scholar
  24. 24.
    Kasslin M, Kangas J, Simula O (1992) Process state monitoring using self organizing maps. In: Aleksander I, Taylor J (eds) Artificial neural networks, vol 2. North Holland, Amsterdam, pp 1531–1534Google Scholar
  25. 25.
    Kohonen T, Hynninen J, Kangas J, Laaksonen J (1996) SOM_PAK: the self-organizing map program package. Helsinki University of Technology, Laboratory of Computer and Information Science, Espoo, Finland: Technical Report A31Google Scholar
  26. 26.
    Vesanto J, Himberg J, Alhoniemi E, Parhankangas J (2000) SOM Toolbox for Matlab 5. Som Toolbox Team. Helsinki University of Technology, Finland.
  27. 27.
    MacQueen JB (1967) Some Methods for classification and Analysis of Multivariate Observations. Proc 5th Berkeley Symposium on Mathematical Statistics and Probability, Berkeley, University of California Press 1:281–297Google Scholar
  28. 28.
    Jain AK, Dubes RC (1988) Algorithms for clustering data. Prentice Hall, Englewood CliffsGoogle Scholar
  29. 29.
    Jain AK, Murty MN, Flynn PJ (1999) Data clustering: a review. ACM Comput Surv 31:264–323CrossRefGoogle Scholar
  30. 30.
    Kaufman L, Rousseeuw PJ (1990) Finding groups in data: an introduction to cluster analysis. Wiley-Interscience, New YorkGoogle Scholar
  31. 31.
    Rousseeuw PJ (1987) Silhouettes: a graphical aid to the interpretation and validation of cluster analysis. J Comput Appl Math 20:53–65CrossRefGoogle Scholar
  32. 32.
    McGee VE, Carleton WT (1970) Piecewise Regression. J Am Stat Assoc 65:1109–1124CrossRefGoogle Scholar
  33. 33.
    Cleveland WS, Grosse EH, Shyu WM (1992) Local regression models. In: Chambers JM, Hastie TJ (eds) Chapman and Hall, London, pp 309–376Google Scholar
  34. 34.
    Chen Y, Dong G, Han J, Wah BW, Wang J (2002) Multi-dimensional regression analysis of time-series data streams. In: Proceedings of 28th international conference very large data bases, Hongkong, China, pp 323–334Google Scholar
  35. 35.
    Karim MN, Hodge D, Simon L (2003) Data-based modeling and analysis of bioprocesses, Some real experiences. Biotechnol Prog 19:1591–1605CrossRefGoogle Scholar
  36. 36.
    Massey FJ Jr (1951) The Kolmogorov-Smirnov test for goodness of fit. J Am Stat Assoc 46:68–78CrossRefGoogle Scholar
  37. 37.
    Darling DA (1957) The Kolmogorov-Smirnov, Cramer-von Mises Tests. Ann Math Stat 28:823–838CrossRefGoogle Scholar
  38. 38.
    Lilliefors HW (1967) On the Kolmogorov-Smirnov test for normality with mean and variance unknown. J Am Stat Assoc 62:399–402CrossRefGoogle Scholar
  39. 39.
    Hallenbeck PC (2005) Fundamentals of fermentative production of hydrogen. Wat Sci Technol 52(1–2):21–29Google Scholar
  40. 40.
    Nandi R, Sengupta S (1998) Microbial production of hydrogen: an overview. Crit Rev Microbiol 24:61–84CrossRefGoogle Scholar
  41. 41.
    Chang FY, Lin CY (2006) Calcium effect on fermentative hydrogen production in an anaerobic up-flow sludge blanket system. Wat Sci Technol 54(9):105–112CrossRefGoogle Scholar
  42. 42.
    Kim DH, Han SK, Kim SH, Shin HS (2006) Effect of gas sparging on continuous hydrogen production. Int J Hydrogen Energy 31:2158–2169CrossRefGoogle Scholar
  43. 43.
    Kim SH, Han SK, Shin HS (2006) Effect of substrate concentration on hydrogen production and 16S rDNA-based analysis of the microbial community in a continuous fermenter. Process Biochem 41:199–207CrossRefGoogle Scholar
  44. 44.
    Lin CN, Wu SY, Chang JS (2006) Fermentative hydrogen production with a draft tube fluidized bed reactor containing silicone-gel-immobilized anaerobic sludge. Int J Hydrogen Energy 31:2200–2210CrossRefGoogle Scholar
  45. 45.
    Lin CY, Hung CH, Chen CH, Chung WT, Cheng LH (2006) Effects of initial cultivation pH on fermentative hydrogen production from xylose using natural mixed cultures. Process Biochem 41:1383–1390CrossRefGoogle Scholar
  46. 46.
    Wu SY, Hung CH, Lin CN, Chen HW, Lee AS, Chang JS (2006) Fermentative hydrogen production and bacterial community structure in high-rate anaerobic bioreactors containing silicone-immobilized and self-flocculated sludge. Biotechnol Bioeng 93:934–946CrossRefGoogle Scholar
  47. 47.
    Ren NQ, Gong ML (2006) Acclimation strategy of a biohydrogen producing population in a continuous-flow reactor with carbohydrate fermentation. Eng Life Sci 6:403–409CrossRefGoogle Scholar
  48. 48.
    Blackwood AC, Neish AC, Ledingham GA (1956) Dissimilation of glucose at controlled pH values by pigmented and non-pigmented strains of Escherichia coli. J Bacteriol 72:497–499CrossRefGoogle Scholar
  49. 49.
    Cheong DY, Hansen CL (2006) Acidogenesis characteristics of natural, mixed anaerobes converting carbohydrate-rich synthetic waste water to hydrogen. Process Biochem 41:1736–1745CrossRefGoogle Scholar
  50. 50.
    Hussy I, Hawkes FR, Dinsdale R, Hawkes DL (2003) Continuous fermentative hydrogen production from a wheat starch co-product by mixed microflora. Biotechnol Bioeng 84:619–626CrossRefGoogle Scholar
  51. 51.
    Hawkes FR, Dinsdale R, Hawkes DL, Hussy I (2002) Sustainable fermentative hydrogen production: challenges for process optimisation. Int J Hydrogen Energy 27:1339–1347CrossRefGoogle Scholar
  52. 52.
    Mizuno O, Dinsdale R, Hawkes FR, Hawkes DL, Noike T (2000) Enhancement of hydrogen production from glucose by nitrogen gas sparging. Bioresour Technol 73:59–65CrossRefGoogle Scholar
  53. 53.
    Liang TM, Cheng SS, Wu KL (2002) Behavioral study on hydrogen fermentation reactor installed with silicone rubber membrane. Int J Hydrogen Energy 27:1157–1165CrossRefGoogle Scholar
  54. 54.
    Teplyakov VV, Gassanova LG, Sostina EG, Slepova EV, Modigell M, Netrusov AI (2002) Lab-scale bioreactor integrated with active membrane system for hydrogen production: experience and prospects. Int J Hydrogen Energy 27:1149–1155CrossRefGoogle Scholar
  55. 55.
    Kataoka N, Miya A, Kiriyama K (1997) Studies on hydrogen production by continuous culture system of hydrogen-producing anaerobic bacteria. Water Sci Technol 36(6–7):41–47CrossRefGoogle Scholar
  56. 56.
    Chen CC, Lin CY (2003) Using sucrose as a substrate in an anaerobic hydrogen producing reactor. Adv Environ Res 7:695–699CrossRefGoogle Scholar
  57. 57.
    Lin CY, Lee CY, Tseng IC, Shiao IZ (2006) Biohydrogen production from sucrose using base-enriched anaerobic mixed microflora. Process Biochem 41:915–919CrossRefGoogle Scholar

Copyright information

© Springer-Verlag 2008

Authors and Affiliations

  • Nikhil
    • 1
    • 2
  • Perttu E. P. Koskinen
    • 2
  • Ari Visa
    • 1
  • Anna H. Kaksonen
    • 2
  • Jaakko A. Puhakka
    • 2
  • Olli Yli-Harja
    • 1
  1. 1.Department of Signal ProcessingTampere University of TechnologyTampereFinland
  2. 2.Department of Chemistry and BioengineeringTampere University of TechnologyTampereFinland

Personalised recommendations